© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4304
    Prev
    Next
    INDEX
    Explanations

    Date vs values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilib
    -0.06
    زÙħ
    -0.06
    åĪĨ以ä¸Ĭ
    -0.06
    ฯ
    -0.06
    ä½Ĩä¹Ł
    -0.06
    ontaine
    -0.06
    -0.06
    ä¸ŃåĽ½ç»ıæµİç½ij
    -0.06
     Reinh
    -0.05
     ×Ķ×IJ×Ļ
    -0.05
    POSITIVE LOGITS
    sworth
    0.07
    ernal
    0.07
    ãģ¾ãģĦ
    0.07
    ouncer
    0.07
    зÑĥм
    0.07
    å°ı妹
    0.07
    uyá»ĥn
    0.07
    SSF
    0.07
    عÙħÙĦ
    0.07
    Authorize
    0.07
    Activations Density 0.165%

    No Known Activations